process-siren

Converts process descriptions, bullet steps, ASCII art, markdown tables, and prose workflows in SKILL.md, agent prompts, and CLAUDE.md into Mermaid — the formal instruction language for AI agents. Invoke when a section contains conditional logic, branching decisions, or multi-step sequences expressed as prose or bullets that an AI agent must follow precisely. Mermaid gives AI readers unambiguous branching (every edge is explicit), discrete step count (nothing collapsed), evaluable conditions (diamonds state observable facts), and explicit terminal states. Output fidelity criterion — every step in the source is a node in the diagram; no step is merged, summarized, or omitted.

Process quality methodology for the process-siren agent — use before or during Mermaid conversion when the source process shows ambiguity, missing decisions, undefined actors, vague conditions, or structural weakness. Provides triage sequence, excellence criteria, and an improvement framework drawn from Lean, Six Sigma, BPR, Design Thinking, Systems Thinking, and Theory of Constraints. Activates when source content is poorly structured enough that converting it as-is would encode wrong behavior for AI readers.

Mermaid diagram syntax reference for all diagram types — flowchart, sequence, class, state, ER, gantt, git graph, mindmap, timeline, user journey, pie, quadrant, XY chart, block, sankey, C4, kanban, and more. Use when constructing or debugging any Mermaid diagram definition.

Optimize processes in a file or directory by converting prose/bullet workflows to Mermaid diagrams — delegates to the process-siren agent. Use when given a single SKILL.md, agent file, CLAUDE.md, or rules file to convert, or a directory containing any of those. Supports --dry-run or --report for read-only planning mode.